all InfoSec news
Privacy Amplification for Matrix Mechanisms
May 7, 2024, 4:12 a.m. | Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
cs.CR updates on arXiv.org arxiv.org
Abstract: Privacy amplification exploits randomness in data selection to provide tighter differential privacy (DP) guarantees. This analysis is key to DP-SGD's success in machine learning, but, is not readily applicable to the newer state-of-the-art algorithms. This is because these algorithms, known as DP-FTRL, use the matrix mechanism to add correlated noise instead of independent noise as in DP-SGD.
In this paper, we propose "MMCC", the first algorithm to analyze privacy amplification via sampling for any generic …
algorithms amplification analysis art arxiv cs.cr cs.lg data differential privacy exploits key machine machine learning matrix mechanism noise privacy randomness state the matrix
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
CyberSOC Technical Lead
@ Integrity360 | Sandyford, Dublin, Ireland
Cyber Security Strategy Consultant
@ Capco | New York City
Cyber Security Senior Consultant
@ Capco | Chicago, IL
Sr. Product Manager
@ MixMode | Remote, US
Corporate Intern - Information Security (Year Round)
@ Associated Bank | US WI Remote
Senior Offensive Security Engineer
@ CoStar Group | US-DC Washington, DC